@article{li_lin_2024, title={Connected Chromatin Amplifies Acetylation-modulated Nucleosome Interactions}, url={https://doi.org/10.1101/2024.10.11.617935}, DOI={10.1101/2024.10.11.617935}, abstractNote={Histone acetylation is a key regulatory post-translational modification closely associated with gene transcription. In particular, H4K16 acetylation (H4K16ac) is a crucial gene activation marker that induces an open chromatin configuration. While previous studies have explored the effects of H4K16ac on nucleosome interactions, how this local modification affects higher-order chromatin organization remains unclear. To bridge the chemical modifications of these histone tail lysine residues to global chromatin structure, we utilized a residue-resolution coarse-grained chromatin model and enhanced sampling techniques to simulate charge-neutralization effects of histone acetylation on nucleosome stability, inter-nucleosome interactions, and higher-order chromatin structure. Our simulations reveal that H4K16ac stabilizes a single nucleosome due to the reduced entropic contribution of histone tails during DNA unwrapping. In addition, acetylation modestly weakens inter-nucleosome interactions by diminishing contacts between histone tails, DNA, and nucleosome acidic patches. These weakened interactions are amplified when nucleosomes are connected by linker DNA, whose fluctuation causes significant chromatin destacking and decompaction, exposing nucleosomes for transcriptional activity. Our findings suggest that the geometric constraint imposed by chromatin DNA plays a critical role in driving chromatin structural reorganization upon post-translational modifications.}, author={Li, Rina and Lin, Xingcheng}, year={2024}, month={Oct} } @article{lin_zhang_2024, title={Explicit Ion Modeling Predicts Physicochemical Interactions for Chromatin Organization}, url={https://doi.org/10.7554/eLife.90073.2}, DOI={10.7554/eLife.90073.2}, abstractNote={Molecular mechanisms that dictate chromatin organization in vivo are under active investigation, and the extent to which intrinsic interactions contribute to this process remains debatable. A central quantity for evaluating their contribution is the strength of nucleosome-nucleosome binding, which previous experiments have estimated to range from 2 to 14 k B T . We introduce an explicit ion model to dramatically enhance the accuracy of residue-level coarse-grained modeling approaches across a wide range of ionic concentrations. This model allows for de novo predictions of chromatin organization and remains computationally efficient, enabling large-scale conformational sampling for free energy calculations. It reproduces the energetics of protein-DNA binding and unwinding of single nucleosomal DNA, and resolves the differential impact of mono and divalent ions on chromatin conformations. Moreover, we showed that the model can reconcile various experiments on quantifying nucleosomal interactions, providing an explanation for the large discrepancy between existing estimations. We predict the interaction strength at physiological conditions to be 9 k B T , a value that is nonetheless sensitive to DNA linker length and the presence of linker histones. Our study strongly supports the contribution of physicochemical interactions to the phase behavior of chromatin aggregates and chromatin organization inside the nucleus. }, author={Lin, Xingcheng and Zhang, Bin}, year={2024}, month={Jan} } @article{lin_zhang_2024, title={Explicit ion modeling predicts physicochemical interactions for chromatin organization}, url={https://doi.org/10.7554/eLife.90073.3}, DOI={10.7554/eLife.90073.3}, abstractNote={Molecular mechanisms that dictate chromatin organization in vivo are under active investigation, and the extent to which intrinsic interactions contribute to this process remains debatable. A central quantity for evaluating their contribution is the strength of nucleosome-nucleosome binding, which previous experiments have estimated to range from 2 to 14 kBT. We introduce an explicit ion model to dramatically enhance the accuracy of residue-level coarse-grained modeling approaches across a wide range of ionic concentrations. This model allows for de novo predictions of chromatin organization and remains computationally efficient, enabling large-scale conformational sampling for free energy calculations. It reproduces the energetics of protein-DNA binding and unwinding of single nucleosomal DNA, and resolves the differential impact of mono- and divalent ions on chromatin conformations. Moreover, we showed that the model can reconcile various experiments on quantifying nucleosomal interactions, providing an explanation for the large discrepancy between existing estimations. We predict the interaction strength at physiological conditions to be 9 kBT, a value that is nonetheless sensitive to DNA linker length and the presence of linker histones. Our study strongly supports the contribution of physicochemical interactions to the phase behavior of chromatin aggregates and chromatin organization inside the nucleus.}, journal={eLife}, author={Lin, Xingcheng and Zhang, Bin}, year={2024}, month={Jan} } @article{zhang_silvernail_lin_lin_2024, title={Interpretable Protein-DNA Interactions Captured by Structure-based Optimization}, url={https://doi.org/10.1101/2024.05.26.595895}, DOI={10.1101/2024.05.26.595895}, abstractNote={Abstract Sequence-specific DNA recognition underlies essential processes in gene regulation, yet predictive methods for simultaneous prediction of genome-wide DNA recognition sites and their binding affinity remain lacking. Here, we present IDEA, an interpretable residue-level biophysical model capable of predicting binding sites and strengths of DNA-binding proteins across the genome. By leveraging the sequence-structure relationship from known protein-DNA complexes, IDEA learns an energy model enabling direct interpretation of physicochemical interactions among individual amino acids and nucleotides. Using transcription factors as examples, we demonstrate that this energy model accurately predicts genomic DNA recognition sites and their binding strengths. Additionally, the IDEA model is integrated into a coarse-grained simulation framework that accurately captures the absolute protein-DNA binding free energies. Overall, IDEA provides an integrated computational platform alleviating experimental costs and biases in assessing DNA recognition and can be utilized for mechanistic studies of various DNA-recognition processes.}, author={Zhang, Yafan and Silvernail, Irene and Lin, Zhuyang and Lin, Xingcheng}, year={2024}, month={May} } @article{wang_lin_chau_onuchic_levine_george_2024, title={RACER-m leverages structural features for sparse T cell specificity prediction}, volume={10}, ISSN={["2375-2548"]}, url={https://doi.org/10.1126/sciadv.adl0161}, DOI={10.1126/sciadv.adl0161}, abstractNote={Reliable prediction of T cell specificity against antigenic signatures is a formidable task, complicated by the immense diversity of T cell receptor and antigen sequence space and the resulting limited availability of training sets for inferential models. Recent modeling efforts have demonstrated the advantage of incorporating structural information to overcome the need for extensive training sequence data, yet disentangling the heterogeneous TCR-antigen interface to accurately predict MHC-allele-restricted TCR-peptide interactions has remained challenging. Here, we present RACER-m, a coarse-grained structural model leveraging key biophysical information from the diversity of publicly available TCR-antigen crystal structures. Explicit inclusion of structural content substantially reduces the required number of training examples and maintains reliable predictions of TCR-recognition specificity and sensitivity across diverse biological contexts. Our model capably identifies biophysically meaningful point-mutant peptides that affect binding affinity, distinguishing its ability in predicting TCR specificity of point-mutants from alternative sequence-based methods. Its application is broadly applicable to studies involving both closely related and structurally diverse TCR-peptide pairs.}, number={20}, journal={SCIENCE ADVANCES}, author={Wang, Ailun and Lin, Xingcheng and Chau, Kevin Ng and Onuchic, Jose N. and Levine, Herbert and George, Jason T.}, year={2024}, month={May} } @article{shibata_lin_onuchic_yura_cheng_2024, title={Residue coevolution and mutational landscape for OmpR and NarL response regulator subfamilies}, volume={123}, ISSN={["1542-0086"]}, DOI={10.1016/j.bpj.2024.01.028}, abstractNote={DNA-binding response regulators (DBRRs) are a broad class of proteins that operate in tandem with their partner kinase proteins to form two-component signal transduction systems in bacteria. Typical DBRRs are composed of two domains where the conserved N-terminal domain accepts transduced signals and the evolutionarily diverse C-terminal domain binds to DNA. These domains are assumed to be functionally independent, and hence recombination of the two domains should yield novel DBRRs of arbitrary input/output response, which can be used as biosensors. This idea has been proved to be successful in some cases; yet, the error rate is not trivial. Improvement of the success rate of this technique requires a deeper understanding of the linker-domain and inter-domain residue interactions, which have not yet been thoroughly examined. Here, we studied residue coevolution of DBRRs of the two main subfamilies (OmpR and NarL) using large collections of bacterial amino acid sequences to extensively investigate the evolutionary signatures of linker-domain and inter-domain residue interactions. Coevolutionary analysis uncovered evolutionarily selected linker-domain and inter-domain residue interactions of known experimental structures, as well as previously unknown inter-domain residue interactions. We examined the possibility of these inter-domain residue interactions as contacts that stabilize an inactive conformation of the DBRR where DNA binding is inhibited for both subfamilies. The newly gained insights on linker-domain/inter-domain residue interactions and shared inactivation mechanisms improve the understanding of the functional mechanism of DBRRs, providing clues to efficiently create functional DBRR-based biosensors. Additionally, we show the feasibility of applying coevolutionary landscape models to predict the functionality of domain-swapped DBRR proteins. The presented result demonstrates that sequence information can be used to filter out bioengineered DBRR proteins that are predicted to be nonfunctional due to a high negative predictive value.}, number={6}, journal={BIOPHYSICAL JOURNAL}, author={Shibata, Mayu and Lin, Xingcheng and Onuchic, Jose N. and Yura, Kei and Cheng, Ryan R.}, year={2024}, month={Mar}, pages={681–692} } @article{lin_zhang_2023, title={Explicit Ion Modeling Predicts Physicochemical Interactions for Chromatin Organization}, url={https://doi.org/10.1101/2023.05.16.541030}, DOI={10.1101/2023.05.16.541030}, abstractNote={AbstractMolecular mechanisms that dictate chromatin organizationin vivoare under active investigation, and the extent to which intrinsic interactions contribute to this process remains debatable. A central quantity for evaluating their contribution is the strength of nucleosome-nucleosome binding, which previous experiments have estimated to range from 2 to 14kBT. We introduce an explicit ion model to dramatically enhance the accuracy of residue-level coarse-grained modeling approaches across a wide range of ionic concentrations. This model allows forde novopredictions of chromatin organization and remains computationally efficient, enabling large-scale conformational sampling for free energy calculations. It reproduces the energetics of protein-DNA binding and unwinding of single nucleosomal DNA, and resolves the differential impact of mono and divalent ions on chromatin conformations. Moreover, we showed that the model can reconcile various experiments on quantifying nucleosomal interactions, providing an explanation for the large discrepancy between existing estimations. We predict the interaction strength at physiological conditions to be 9kBT, a value that is nonetheless sensitive to DNA linker length and the presence of linker histones. Our study strongly supports the contribution of physicochemical interactions to the phase behavior of chromatin aggregates and chromatin organization inside the nucleus.}, author={Lin, Xingcheng and Zhang, Bin}, year={2023}, month={May} } @article{lin_zhang_2023, title={Explicit Ion Modeling Predicts Physicochemical Interactions for Chromatin Organization}, url={https://doi.org/10.7554/eLife.90073.1}, DOI={10.7554/eLife.90073.1}, abstractNote={Molecular mechanisms that dictate chromatin organization in vivo are under active investigation, and the extent to which intrinsic interactions contribute to this process remains debatable. A central quantity for evaluating their contribution is the strength of nucleosome-nucleosome binding, which previous experiments have estimated to range from 2 to 14 kBT . We introduce an explicit ion model to dramatically enhance the accuracy of residue-level coarse-grained modeling approaches across a wide range of ionic concentrations. This model allows for de novo predictions of chromatin organization and remains computationally efficient, enabling large-scale conformational sampling for free energy calculations. It reproduces the energetics of protein-DNA binding and unwinding of single nucleosomal DNA, and resolves the differential impact of mono and divalent ions on chromatin conformations. Moreover, we showed that the model can reconcile various experiments on quantifying nucleosomal interactions, providing an explanation for the large discrepancy between existing estimations. We predict the interaction strength at physiological conditions to be 9 kBT , a value that is nonetheless sensitive to DNA linker length and the presence of linker histones. Our study strongly supports the contribution of physicochemical interactions to the phase behavior of chromatin aggregates and chromatin organization inside the nucleus.}, author={Lin, Xingcheng and Zhang, Bin}, year={2023}, month={Aug} } @article{lin_zhang_2024, title={Explicit ion modeling predicts physicochemical interactions for chromatin organization}, volume={12}, ISSN={["2050-084X"]}, url={https://doi.org/10.7554/eLife.90073}, DOI={10.7554/eLife.90073}, abstractNote={Molecular mechanisms that dictate chromatin organization in vivo are under active investigation, and the extent to which intrinsic interactions contribute to this process remains debatable. A central quantity for evaluating their contribution is the strength of nucleosome-nucleosome binding, which previous experiments have estimated to range from 2 to 14 kBT. We introduce an explicit ion model to dramatically enhance the accuracy of residue-level coarse-grained modeling approaches across a wide range of ionic concentrations. This model allows for de novo predictions of chromatin organization and remains computationally efficient, enabling large-scale conformational sampling for free energy calculations. It reproduces the energetics of protein-DNA binding and unwinding of single nucleosomal DNA, and resolves the differential impact of mono- and divalent ions on chromatin conformations. Moreover, we showed that the model can reconcile various experiments on quantifying nucleosomal interactions, providing an explanation for the large discrepancy between existing estimations. We predict the interaction strength at physiological conditions to be 9 kBT, a value that is nonetheless sensitive to DNA linker length and the presence of linker histones. Our study strongly supports the contribution of physicochemical interactions to the phase behavior of chromatin aggregates and chromatin organization inside the nucleus.}, journal={ELIFE}, author={Lin, Xingcheng and Zhang, Bin}, year={2024}, month={Jan} } @article{wang_lin_chau_onuchic_levine_george_2023, title={RACER-m Leverages Structural Features for Sparse T Cell Specificity Prediction}, volume={8}, url={http://dx.doi.org/10.1101/2023.08.06.552190}, DOI={10.1101/2023.08.06.552190}, abstractNote={AbstractReliable prediction of T cell specificity against antigenic signatures is a formidable task, complicated primarily by the immense diversity of T cell receptor and antigen sequence space and the resulting limited availability of training sets for inferential models. Recent modeling efforts have demonstrated the advantage of incorporating structural information to overcome the need for extensive training sequence data, yet disentangling the heterogeneous TCR-antigen structural interface to accurately predict the MHC-allele-restricted TCR-peptide binding interactions remained challenging. Here, we present RACER-m, a coarse-grained structural template model leveraging key biophysical information from the diversity of publicly available TCR-antigen crystal structures. We find explicit inclusion of structural content substantially reduces the required number of training examples for reliable prediction of TCR-recognition specificity and sensitivity across diverse biological contexts. We demonstrate that our structural model capably identifies biophysically meaningful point-mutants that affect overall binding affinity, distinguishing its ability in predicting TCR specificity of point mutants peptides from alternative sequence-based methods. Collectively, our approach combines biophysical and inferential learning-based methods to predict TCR-peptide binding events using sparse training data. Its application is broadly applicable to studies involving both closely-related and structurally diverse TCR-peptide pairs.}, publisher={Cold Spring Harbor Laboratory}, author={Wang, Ailun and Lin, Xingcheng and Chau, Kevin Ng and Onuchic, José N. and Levine, Herbert and George, Jason T}, year={2023}, month={Aug} } @article{guo_chen_manna_lin_scott_chen_hoffman_zhang_schlau-cohen_2023, title={Single-molecule acceptor rise time (smART) FRET for nanoscale distance sensitivity}, url={https://doi.org/10.1101/2023.03.15.532809}, DOI={10.1101/2023.03.15.532809}, abstractNote={AbstractThe structure, dynamics, and binding of individual biomolecules have been extensively investigated using single-molecule Förster resonance energy transfer (smFRET) as a ‘spectroscopic ruler.’ The FRET efficiency between a fluorophore pair is used to measure distances in the several nanometer range. Existing approaches to detect closer distances come at the expense of sensitivity to longer distances. Here, we introduce single-molecule acceptor rise-time (smART) FRET that spans closer and longer distances. The acceptor rise time encodes the FRET rate, which scales polynomially with distance and thus has a steep dependence that expands the working range by 50%. High precision and accuracy is achieved through the spectroscopic separation between the rise time and the photophysical fluctuations that obfuscate other FRET readouts. Using the nanoscale sensitivity, we resolved the architectures of DNA bound to the single-stranded binding protein fromE. coli, demonstrating the ability of smART FRET to elucidate the complex behaviors of biomolecules.}, author={Guo, Jiajia and Chen, Xuyan and Manna, Premashis and Lin, Xingcheng and Scott, Madelyn N. and Chen, Wei Jia and Hoffman, Mikaila and Zhang, Bin and Schlau-Cohen, Gabriela S.}, year={2023}, month={Mar} } @article{liu_lin_zhang_2022, title={Chromatin fiber breaks into clutches under tension and crowding}, volume={50}, ISSN={0305-1048 1362-4962}, url={http://dx.doi.org/10.1093/nar/gkac725}, DOI={10.1093/nar/gkac725}, abstractNote={Abstract The arrangement of nucleosomes inside chromatin is of extensive interest. While in vitro experiments have revealed the formation of 30 nm fibers, most in vivo studies have failed to confirm their presence in cell nuclei. To reconcile the diverging experimental findings, we characterized chromatin organization using a residue-level coarse-grained model. The computed force–extension curve matches well with measurements from single-molecule experiments. Notably, we found that a dodeca-nucleosome in the two-helix zigzag conformation breaks into structures with nucleosome clutches and a mix of trimers and tetramers under tension. Such unfolded configurations can also be stabilized through trans interactions with other chromatin chains. Our study suggests that unfolding from chromatin fibers could contribute to the irregularity of in vivo chromatin configurations. We further revealed that chromatin segments with fibril or clutch structures engaged in distinct binding modes and discussed the implications of these inter-chain interactions for a potential sol–gel phase transition.}, number={17}, journal={Nucleic Acids Research}, publisher={Oxford University Press (OUP)}, author={Liu, Shuming and Lin, Xingcheng and Zhang, Bin}, year={2022}, month={Aug}, pages={9738–9747} } @article{chau_george_onuchic_lin_levine_2022, title={Contact map dependence of a T-cell receptor binding repertoire}, url={https://doi.org/10.1103/PhysRevE.106.014406}, DOI={10.1103/PhysRevE.106.014406}, abstractNote={The T-cell arm of the adaptive immune system provides the host protection against unknown pathogens by discriminating between host and foreign material. This discriminatory capability is achieved by the creation of a repertoire of cells each carrying a T-cell receptor (TCR) specific to non-self-antigens displayed as peptides bound to the major histocompatibility complex (pMHC). The understanding of the dynamics of the adaptive immune system at a repertoire level is complex, due to both the nuanced interaction of a TCR-pMHC pair and to the number of different possible TCR-pMHC pairings, making computationally exact solutions currently unfeasible. To gain some insight into this problem, we study an affinity-based model for TCR-pMHC binding in which a crystal structure is used to generate a distance-based contact map that weights the pairwise amino acid interactions. We find that the TCR-pMHC binding energy distribution strongly depends both on the number of contacts and the repeat structure allowed by the topology of the contact map of choice; this in turn influences T-cell recognition probability during negative selection, with higher variances leading to higher survival probabilities. In addition, we quantify the degree to which neoantigens with mutations in sites with higher contacts are recognized at a higher rate.}, journal={Physical Review E}, author={Chau, Kevin Ng and George, Jason T. and Onuchic, José N. and Lin, Xingcheng and Levine, Herbert}, year={2022}, month={Jul} } @article{srinivasan_regmi_lin_dreyer_chen_quinn_he_coleman_carraway_zhang_et al._2022, title={Ligand-induced transmembrane conformational coupling in monomeric EGFR}, volume={13}, ISSN={2041-1723}, url={http://dx.doi.org/10.1038/s41467-022-31299-z}, DOI={10.1038/s41467-022-31299-z}, abstractNote={AbstractSingle pass cell surface receptors regulate cellular processes by transmitting ligand-encoded signals across the plasma membrane via changes to their extracellular and intracellular conformations. This transmembrane signaling is generally initiated by ligand binding to the receptors in their monomeric form. While subsequent receptor-receptor interactions are established as key aspects of transmembrane signaling, the contribution of monomeric receptors has been challenging to isolate due to the complexity and ligand-dependence of these interactions. By combining membrane nanodiscs produced with cell-free expression, single-molecule Förster Resonance Energy Transfer measurements, and molecular dynamics simulations, we report that ligand binding induces intracellular conformational changes within monomeric, full-length epidermal growth factor receptor (EGFR). Our observations establish the existence of extracellular/intracellular conformational coupling within a single receptor molecule. We implicate a series of electrostatic interactions in the conformational coupling and find the coupling is inhibited by targeted therapeutics and mutations that also inhibit phosphorylation in cells. Collectively, these results introduce a facile mechanism to link the extracellular and intracellular regions through the single transmembrane helix of monomeric EGFR, and raise the possibility that intramolecular transmembrane conformational changes upon ligand binding are common to single-pass membrane proteins.}, number={1}, journal={Nature Communications}, publisher={Springer Science and Business Media LLC}, author={Srinivasan, Shwetha and Regmi, Raju and Lin, Xingcheng and Dreyer, Courtney A. and Chen, Xuyan and Quinn, Steven D. and He, Wei and Coleman, Matthew A. and Carraway, Kermit L., III and Zhang, Bin and et al.}, year={2022}, month={Jul} } @article{liu_lin_zhang_2021, title={Chromatin fiber breaks into clutches under tension and crowding}, volume={11}, url={https://doi.org/10.1101/2021.11.16.468645}, DOI={10.1101/2021.11.16.468645}, abstractNote={AbstractThe arrangement of nucleosomes inside chromatin is of extensive interest. While in vitro experiments have revealed the formation of 30 nm fibers, most in vivo studies have failed to confirm their presence in cell nuclei. To reconcile the diverging experimental findings, we characterized chromatin organization using a near atomistic model. The computed force-extension curve matches well with measurements from single-molecule experiments. Notably, we found that a dodeca-nucleosome in the two-helix zigzag conformation breaks into structures with nucleosome clutches and a mix of trimers and tetramers under tension. Such unfolded configurations can also be stabilized through trans interactions with other chromatin chains. Our study supports a hypothesis that disordered, in vivo chromatin configurations arise as folding intermediates from regular fibril structures. We further revealed that chromatin segments with fibril or clutch structures engaged in distinct binding modes and discussed the implications of these inter-chain interactions for a potential sol-gel phase transition.}, publisher={Cold Spring Harbor Laboratory}, author={Liu, Shuming and Lin, Xingcheng and Zhang, Bin}, year={2021}, month={Nov} } @article{lin_leicher_liu_zhang_2021, title={Cooperative DNA looping by PRC2 complexes}, volume={49}, ISSN={0305-1048 1362-4962}, url={http://dx.doi.org/10.1093/nar/gkab441}, DOI={10.1093/nar/gkab441}, abstractNote={Abstract Polycomb repressive complex 2 (PRC2) is an essential protein complex that silences gene expression via post-translational modifications of chromatin. This paper combined homology modeling, atomistic and coarse-grained molecular dynamics simulations, and single-molecule force spectroscopy experiments to characterize both its full-length structure and PRC2-DNA interactions. Using free energy calculations with a newly parameterized protein-DNA force field, we studied a total of three potential PRC2 conformations and their impact on DNA binding and bending. Consistent with cryo-EM studies, we found that EZH2, a core subunit of PRC2, provides the primary interface for DNA binding, and its curved surface can induce DNA bending. Our simulations also predicted the C2 domain of the SUZ12 subunit to contact DNA. Multiple PRC2 complexes bind with DNA cooperatively via allosteric communication through the DNA, leading to a hairpin-like looped configuration. Single-molecule experiments support PRC2-mediated DNA looping and the role of AEBP2 in regulating such loop formation. The impact of AEBP2 can be partly understood from its association with the C2 domain, blocking C2 from DNA binding. Our study suggests that accessory proteins may regulate the genomic location of PRC2 by interfering with its DNA interactions.}, number={11}, journal={Nucleic Acids Research}, publisher={Oxford University Press (OUP)}, author={Lin, Xingcheng and Leicher, Rachel and Liu, Shixin and Zhang, Bin}, year={2021}, month={May}, pages={6238–6248} } @article{oliveira junior_lin_kulkarni_onuchic_roy_leite_2021, title={Exploring Energy Landscapes of Intrinsically Disordered Proteins: Insights into Functional Mechanisms}, volume={17}, ISSN={1549-9618 1549-9626}, url={http://dx.doi.org/10.1021/acs.jctc.1c00027}, DOI={10.1021/acs.jctc.1c00027}, abstractNote={Intrinsically disordered proteins (IDPs) lack a rigid three-dimensional structure and populate a polymorphic ensemble of conformations. Because of the lack of a reference conformation, their energy landscape representation in terms of reaction coordinates presents a daunting challenge. Here, our newly developed energy landscape visualization method (ELViM), a reaction coordinate-free approach, shows its prime application to explore frustrated energy landscapes of an intrinsically disordered protein, prostate-associated gene 4 (PAGE4). PAGE4 is a transcriptional coactivator that potentiates the oncogene c-Jun. Two kinases, namely, HIPK1 and CLK2, phosphorylate PAGE4, generating variants phosphorylated at different serine/threonine residues (HIPK1-PAGE4 and CLK2-PAGE4, respectively) with opposing functions. While HIPK1-PAGE4 predominantly phosphorylates Thr51 and potentiates c-Jun, CLK2-PAGE4 hyperphosphorylates PAGE4 and attenuates transactivation. To understand the underlying mechanisms of conformational diversity among different phosphoforms, we have analyzed their atomistic trajectories simulated using AWSEM forcefield, and the energy landscapes were elucidated using ELViM. This method allows us to identify and compare the population distributions of different conformational ensembles of PAGE4 phosphoforms using the same effective phase space. The results reveal a predominant conformational ensemble with an extended C-terminal segment of WT PAGE4, which exposes a functional residue Thr51, implying its potential of undertaking a fly-casting mechanism while binding to its cognate partner. In contrast, for HIPK1-PAGE4, a compact conformational ensemble enhances its population sequestering phosphorylated-Thr51. This clearly explains the experimentally observed weaker affinity of HIPK1-PAGE4 for c-Jun. ELViM appears as a powerful tool, especially to analyze the highly frustrated energy landscape representation of IDPs where appropriate reaction coordinates are hard to apprehend.}, number={5}, journal={Journal of Chemical Theory and Computation}, publisher={American Chemical Society (ACS)}, author={Oliveira Junior, Antonio B. and Lin, Xingcheng and Kulkarni, Prakash and Onuchic, José N. and Roy, Susmita and Leite, Vitor B. P.}, year={2021}, month={Apr}, pages={3178–3187} } @article{antonio b. oliveira_lin_kulkarni_onuchic_roy_leite_2021, title={Exploring Energy Landscapes of Intrinsically Disordered Proteins: Insights into Functional Mechanisms}, url={https://doi.org/10.1101/2021.01.28.428595}, DOI={10.1101/2021.01.28.428595}, abstractNote={Abstract Intrinsically disordered proteins (IDPs) lack a rigid 3D structure and populate a polymorphic ensemble of conformations. Because of the lack of a reference conformation, their energy landscape representation in terms of reaction coordinates presents a daunting challenge. Here, our newly developed Energy Landscape Visualization Method (ELViM), a reaction coordinate-free approach, shows its prime application to explore frustrated energy landscapes of an intrinsically disordered protein, Prostate-Associated Gene 4 (PAGE4). PAGE4 is a transcriptional coactivator that potentiates the oncogene c-Jun. Two kinases, namely HIPK1 and CLK2, phosphorylate PAGE4 generating variants phosphorylated at different serine/threonine residues (HIPK1-PAGE4 and CLK2-PAGE4, respectively) with opposing functions. While HIPK1-PAGE4 predominantly phosphorylates Thr51 and potentiates c-Jun, CLK2-PAGE4 hyper-phosphorylates PAGE4 and attenuates transactivation. To understand the underlying mechanisms of conformational diversity among different phosphoforms, we have analyzed their atomistic trajectories simulated using AWSEM forcefield and the energy landscapes were elucidated using ELViM. This method allows us to identify and compare the population distributions of different conformational ensembles of PAGE4 phosphoforms using the same effective phase space. The results reveal a predominant conformational ensemble with an extended C-terminal segment of WT PAGE4, which exposes a functional residue Thr51, implying its potential of undertaking a fly-casting mechanism while binding to its cognate partner. In contrast, for HIPK1-PAGE4, a compact conformational ensemble enhances its population sequestering phosphorylated-Thr51. This clearly explains the experimentally observed weaker affinity of HIPK1-PAGE4 for c-Jun. ELViM appears as a powerful tool especially to analyze the highly-frustrated energy landscape representation of IDPs where appropriate reaction coordinates are hard to apprehend.}, author={Antonio B. Oliveira, Junior and Lin, Xingcheng and Kulkarni, Prakash and Onuchic, José N. and Roy, Susmita and Leite, Vitor B.P.}, year={2021}, month={Jan} } @article{srinivasan_regmi_lin_dreyer_chen_quinn_he_carraway_coleman_zhang_et al._2021, title={Ligand-induced transmembrane conformational coupling in monomeric EGFR}, volume={10}, url={https://doi.org/10.1101/2021.10.28.466294}, DOI={10.1101/2021.10.28.466294}, abstractNote={Single pass cell surface receptors regulate cellular processes by transmitting ligand-encoded signals across the plasma membrane via changes to their extracellular and intracellular conformations. While receptor-receptor interactions are established as key aspects of transmembrane signaling, the contribution from the single helix of a monomeric receptor has been challenging to isolate due to the complexity and ligand-dependence of the receptor-receptor interactions. By combining membrane nanodiscs produced wtih cell-free expression, single-molecule Förster Resonance Energy Transfer measurements, and molecular dynamics simulations, we report that ligand binding induces intracellular conformational changes within monomeric, full-length epidermal growth factor receptor (EGFR). Our observations establish the existence of extracellular/intracellular conformational coupling within a single receptor molecule. We implicate a series of electrostatic interactions in the conformational coupling and find the coupling is inhibited by targeted therapeutics and mutations that also inhibit phosphorylation in cells. Collectively, these results introduce a facile mechanism to link the extracellular and intracellular regions through the single transmembrane helix of monomeric EGFR, and raise the possibility that intramolecular transmembrane conformational changes are common to single-pass membrane proteins.}, publisher={Cold Spring Harbor Laboratory}, author={Srinivasan, Shwetha and Regmi, Raju and Lin, Xingcheng and Dreyer, Courtney A. and Chen, Xuyan and Quinn, Steven D. and He, Wei and Carraway, Kermit L., III and Coleman, Matthew A. and Zhang, Bin and et al.}, year={2021}, month={Oct} } @article{lin_qi_latham_zhang_2021, title={Multiscale modeling of genome organization with maximum entropy optimization}, volume={155}, ISSN={0021-9606 1089-7690}, url={http://dx.doi.org/10.1063/5.0044150}, DOI={10.1063/5.0044150}, abstractNote={Three-dimensional (3D) organization of the human genome plays an essential role in all DNA-templated processes, including gene transcription, gene regulation, and DNA replication. Computational modeling can be an effective way of building high-resolution genome structures and improving our understanding of these molecular processes. However, it faces significant challenges as the human genome consists of over 6 × 109 base pairs, a system size that exceeds the capacity of traditional modeling approaches. In this perspective, we review the progress that has been made in modeling the human genome. Coarse-grained models parameterized to reproduce experimental data via the maximum entropy optimization algorithm serve as effective means to study genome organization at various length scales. They have provided insight into the principles of whole-genome organization and enabled de novo predictions of chromosome structures from epigenetic modifications. Applications of these models at a near-atomistic resolution further revealed physicochemical interactions that drive the phase separation of disordered proteins and dictate chromatin stability in situ. We conclude with an outlook on the opportunities and challenges in studying chromosome dynamics.}, number={1}, journal={The Journal of Chemical Physics}, publisher={AIP Publishing}, author={Lin, Xingcheng and Qi, Yifeng and Latham, Andrew P. and Zhang, Bin}, year={2021}, month={Jul}, pages={010901} } @article{lin_george_schafer_ng chau_birnbaum_clementi_onuchic_levine_2021, title={Rapid assessment of T-cell receptor specificity of the immune repertoire}, volume={1}, ISSN={2662-8457}, url={http://dx.doi.org/10.1038/s43588-021-00076-1}, DOI={10.1038/s43588-021-00076-1}, abstractNote={Accurate assessment of TCR-antigen specificity at the whole immune repertoire level lies at the heart of improved cancer immunotherapy, but predictive models capable of high-throughput assessment of TCR-peptide pairs are lacking. Recent advances in deep sequencing and crystallography have enriched the data available for studying TCR-p-MHC systems. Here, we introduce a pairwise energy model, RACER, for rapid assessment of TCR-peptide affinity at the immune repertoire level. RACER applies supervised machine learning to efficiently and accurately resolve strong TCR-peptide binding pairs from weak ones. The trained parameters further enable a physical interpretation of interacting patterns encoded in each specific TCR-p-MHC system. When applied to simulate thymic selection of an MHC-restricted T-cell repertoire, RACER accurately estimates recognition rates for tumor-associated neoantigens and foreign peptides, thus demonstrating its utility in helping address the large computational challenge of reliably identifying the properties of tumor antigen-specific T-cells at the level of an individual patient's immune repertoire.}, number={5}, journal={Nature Computational Science}, publisher={Springer Science and Business Media LLC}, author={Lin, Xingcheng and George, Jason T. and Schafer, Nicholas P. and Ng Chau, Kevin and Birnbaum, Michael E. and Clementi, Cecilia and Onuchic, José N. and Levine, Herbert}, year={2021}, month={May}, pages={362–373} } @article{ding_lin_zhang_2021, title={Stability and folding pathways of tetra-nucleosome from six-dimensional free energy surface}, volume={12}, ISSN={2041-1723}, url={http://dx.doi.org/10.1038/s41467-021-21377-z}, DOI={10.1038/s41467-021-21377-z}, abstractNote={AbstractThe three-dimensional organization of chromatin is expected to play critical roles in regulating genome functions. High-resolution characterization of its structure and dynamics could improve our understanding of gene regulation mechanisms but has remained challenging. Using a near-atomistic model that preserves the chemical specificity of protein-DNA interactions at residue and base-pair resolution, we studied the stability and folding pathways of a tetra-nucleosome. Dynamical simulations performed with an advanced sampling technique uncovered multiple pathways that connect open chromatin configurations with the zigzag crystal structure. Intermediate states along the simulated folding pathways resemble chromatin configurations reported from in situ experiments. We further determined a six-dimensional free energy surface as a function of the inter-nucleosome distances via a deep learning approach. The zigzag structure can indeed be seen as the global minimum of the surface. However, it is not favored by a significant amount relative to the partially unfolded, in situ configurations. Chemical perturbations such as histone H4 tail acetylation and thermal fluctuations can further tilt the energetic balance to stabilize intermediate states. Our study provides insight into the connection between various reported chromatin configurations and has implications on the in situ relevance of the 30 nm fiber.}, number={1}, journal={Nature Communications}, publisher={Springer Science and Business Media LLC}, author={Ding, Xinqiang and Lin, Xingcheng and Zhang, Bin}, year={2021}, month={Feb} } @article{ding_lin_zhang_2021, title={Stability and folding pathways of tetra-nucleosome from six-dimensional free energy surface}, url={https://doi.org/10.1101/2021.01.06.425601}, DOI={10.1101/2021.01.06.425601}, abstractNote={Abstract The three-dimensional organization of chromatin is expected to play critical roles in regulating genome functions. High-resolution characterization of its structure and dynamics could improve our understanding of gene regulation mechanisms but has remained challenging. Using a near-atomistic model that preserves the chemical specificity of protein-DNA interactions at residue and base-pair resolution, we studied the stability and folding pathways of a tetra-nucleosome. Dynamical simulations performed with an advanced sampling technique uncovered multiple pathways that connect open chromatin configurations with the zigzag crystal structure. Intermediate states along the simulated folding pathways resemble chromatin configurations reported from in situ experiments. We further determined a six-dimensional free energy surface as a function of the inter-nucleosome distances via a deep learning approach. The zigzag structure can indeed be seen as the global minimum of the surface. However, it is not favored by a significant amount relative to the partially unfolded, in situ configurations. Chemical perturbations such as histone H4 tail acetylation and thermal fluctuations can further tilt the energetic balance to stabilize intermediate states. Our study provides insight into the connection between various reported chromatin configurations and has implications on the in situ relevance of the 30nm fiber.}, author={Ding, Xinqiang and Lin, Xingcheng and Zhang, Bin}, year={2021}, month={Jan} } @article{guo_qi_yu_liu_chung_bai_lin_lu_wang_chen_et al._2020, title={Enhancing intracellular accumulation and target engagement of PROTACs with reversible covalent chemistry}, volume={11}, ISSN={2041-1723}, url={http://dx.doi.org/10.1038/s41467-020-17997-6}, DOI={10.1038/s41467-020-17997-6}, abstractNote={AbstractCurrent efforts in the proteolysis targeting chimera (PROTAC) field mostly focus on choosing an appropriate E3 ligase for the target protein, improving the binding affinities towards the target protein and the E3 ligase, and optimizing the PROTAC linker. However, due to the large molecular weights of PROTACs, their cellular uptake remains an issue. Through comparing how different warhead chemistry, reversible noncovalent (RNC), reversible covalent (RC), and irreversible covalent (IRC) binders, affects the degradation of Bruton’s Tyrosine Kinase (BTK), we serendipitously discover that cyano-acrylamide-based reversible covalent chemistry can significantly enhance the intracellular accumulation and target engagement of PROTACs and develop RC-1 as a reversible covalent BTK PROTAC with a high target occupancy as its corresponding kinase inhibitor and effectiveness as a dual functional inhibitor and degrader, a different mechanism-of-action for PROTACs. Importantly, this reversible covalent strategy is generalizable to improve other PROTACs, opening a path to enhance PROTAC efficacy.}, number={1}, journal={Nature Communications}, publisher={Springer Science and Business Media LLC}, author={Guo, Wen-Hao and Qi, Xiaoli and Yu, Xin and Liu, Yang and Chung, Chan-I and Bai, Fang and Lin, Xingcheng and Lu, Dong and Wang, Lingfei and Chen, Jianwei and et al.}, year={2020}, month={Aug} } @article{jin_miller_chen_schafer_lin_chen_phillips_wolynes_2020, title={Molecular-replacement phasing using predicted protein structures from AWSEM-Suite}, volume={7}, ISSN={2052-2525}, url={http://dx.doi.org/10.1107/S2052252520013494}, DOI={10.1107/S2052252520013494}, abstractNote={The phase problem in X-ray crystallography arises from the fact that only the intensities, and not the phases, of the diffracting electromagnetic waves are measured directly. Molecular replacement can often estimate the relative phases of reflections starting with those derived from a template structure, which is usually a previously solved structure of a similar protein. The key factor in the success of molecular replacement is finding a good template structure. When no good solved template exists, predicted structures based partially on templates can sometimes be used to generate models for molecular replacement, thereby extending the lower bound of structural and sequence similarity required for successful structure determination. Here, the effectiveness is examined of structures predicted by a state-of-the-art prediction algorithm, the Associative memory, Water-mediated, Structure and Energy Model Suite (AWSEM-Suite), which has been shown to perform well in predicting protein structures in CASP13 when there is no significant sequence similarity to a solved protein or only very low sequence similarity to known templates. The performance of AWSEM-Suite structures in molecular replacement is discussed and the results show that AWSEM-Suite performs well in providing useful phase information, often performing better than I-TASSER-MR and the previous algorithm AWSEM-Template.}, number={6}, journal={IUCrJ}, publisher={International Union of Crystallography (IUCr)}, author={Jin, Shikai and Miller, Mitchell D. and Chen, Mingchen and Schafer, Nicholas P. and Lin, Xingcheng and Chen, Xun and Phillips, George N., Jr and Wolynes, Peter G.}, year={2020}, month={Oct}, pages={1168–1178} } @article{jin_chen_chen_bueno_lu_schafer_lin_onuchic_wolynes_2020, title={Protein Structure Prediction in CASP13 Using AWSEM-Suite}, volume={16}, ISSN={1549-9618 1549-9626}, url={http://dx.doi.org/10.1021/acs.jctc.0c00188}, DOI={10.1021/acs.jctc.0c00188}, abstractNote={Recently several techniques have emerged that significantly enhance the quality of predictions of protein tertiary structures. In this study, we describe the performance of AWSEM-Suite, an algorithm that incorporates template-based modeling and coevolutionary restraints with a realistic coarse-grained force field, AWSEM. With its roots in neural networks, AWSEM contains both physical and bioinformatical energies that have been optimized using energy landscape theory. AWSEM-Suite participated in CASP13 as a server predictor and generated reliable predictions for most targets. AWSEM-Suite ranked 8th in both the free-modeling category and the hard-to-model category and in one case provided the best submitted prediction. Here we critically discuss the prediction performance of AWSEM-Suite using several examples from different categories in CASP13. Structure prediction tests on these selected targets, two of them being hard-to-model targets, show that AWSEM-Suite can achieve high-resolution structure prediction after incorporating both template guidances and coevolutionary restraints even when homology is weak. For targets with reliable templates (template-easy category) introducing, coevolutionary restraints sometimes damage the overall quality of the predictions. Free energy profile analyses demonstrate however that the incorporation of both of these evolutionarily informed terms effectively increases the funneling of the landscape towards native-like structures while still allowing sufficient flexibility to correct for discrepancies between the correct target structure and the provided guidance. In contrast to other predictors that are exclusively oriented towards structure prediction, the connection of AWSEM-Suite to a statistical mechanical basis and affiliated molecular dynamics and importance sampling simulations makes it suitable for functional explorations.}, number={6}, journal={Journal of Chemical Theory and Computation}, publisher={American Chemical Society (ACS)}, author={Jin, Shikai and Chen, Mingchen and Chen, Xun and Bueno, Carlos and Lu, Wei and Schafer, Nicholas P. and Lin, Xingcheng and Onuchic, José N. and Wolynes, Peter G.}, year={2020}, month={May}, pages={3977–3988} } @article{chen_chen_jin_lu_lin_wolynes_2020, title={Protein Structure Refinement Guided by Atomic Packing Frustration Analysis}, volume={124}, ISSN={1520-6106 1520-5207}, url={http://dx.doi.org/10.1021/acs.jpcb.0c06719}, DOI={10.1021/acs.jpcb.0c06719}, abstractNote={Recent advances in machine learning, bioinformatics, and the understanding of the folding problem have enabled efficient predictions of protein structures with moderate accuracy, even for targets where there is little information from templates. All-atom molecular dynamics simulations provide a route to refine such predicted structures, but unguided atomistic simulations, even when lengthy in time, often fail to eliminate incorrect structural features that would prevent the structure from becoming more energetically favorable owing to the necessity of making large scale motions and to overcoming energy barriers for side chain repacking. In this study, we show that localizing packing frustration at atomic resolution by examining the statistics of the energetic changes that occur when the local environment of a site is changed allows one to identify the most likely locations of incorrect contacts. The global statistics of atomic resolution frustration in structures that have been predicted using various algorithms provide strong indicators of structural quality when tested over a database of 20 targets from previous CASP experiments. Residues that are more correctly located turn out to be more minimally frustrated than more poorly positioned sites. These observations provide a diagnosis of both global and local quality of predicted structures and thus can be used as guidance in all-atom refinement simulations of the 20 targets. Refinement simulations guided by atomic packing frustration turn out to be quite efficient and significantly improve the quality of the structures.}, number={48}, journal={The Journal of Physical Chemistry B}, publisher={American Chemical Society (ACS)}, author={Chen, Mingchen and Chen, Xun and Jin, Shikai and Lu, Wei and Lin, Xingcheng and Wolynes, Peter G.}, year={2020}, month={Sep}, pages={10889–10898} } @article{lin_george_schafer_chau_birnbaum_clementi_onuchic_levine_2021, title={Rapid assessment of T-cell receptor specificity of the immune repertoire}, url={http://dx.doi.org/10.1038/s43588-021-00076-1}, DOI={10.1101/2020.04.06.028415}, abstractNote={AbstractAccurate assessment of TCR-antigen specificity at the whole immune repertoire level lies at the heart of improved cancer immunotherapy, but predictive models capable of high-throughput assessment of TCR-peptide pairs are lacking. Recent advances in deep sequencing and crystallography have enriched the data available for studying TCR-p-MHC systems. Here, we introduce a pairwise energy model, RACER, for rapid assessment of TCR-peptide affinity at the immune repertoire level. RACER applies supervised machine learning to efficiently and accurately resolve strong TCR-peptide binding pairs from weak ones. The trained parameters further enable a physical interpretation of interacting patterns encoded in each specific TCR-p-MHC system. When applied to simulate thymic selection of an MHC-restricted T-cell repertoire, RACER accurately estimates recognition rates for tumor-associated neoantigens and foreign peptides, thus demonstrating its utility in helping address the large computational challenge of reliably identifying the properties of tumor antigen-specific T-cells at the level of an individual patient’s immune repertoire.}, journal={Nature Computational Science}, author={Lin, Xingcheng and George, Jason T. and Schafer, Nicholas P. and Chau, Kevin Ng and Birnbaum, Michael E. and Clementi, Cecilia and Onuchic, José N. and Levine, Herbert}, year={2021}, month={May} } @article{leicher_ge_lin_reynolds_xie_walz_zhang_muir_liu_2020, title={Single-molecule and in silico dissection of the interaction between Polycomb repressive complex 2 and chromatin}, volume={117}, ISSN={0027-8424 1091-6490}, url={http://dx.doi.org/10.1073/pnas.2003395117}, DOI={10.1073/pnas.2003395117}, abstractNote={Significance Polycomb repressive complex 2 (PRC2) is a major epigenetic machinery that maintains transcriptionally silent heterochromatin in the nucleus and plays critical roles in embryonic development and oncogenesis. It is generally thought that PRC2 propagates repressive histone marks by modifying neighboring nucleosomes in strictly linear progression. However, the behavior of PRC2 on native-like chromatin substrates remains incompletely characterized, making the precise mechanism of PRC2-mediated heterochromatin maintenance elusive. Here we use single-molecule force spectroscopy and computational modeling to dissect the interactions between PRC2 and polynucleosome arrays. Our results provide direct evidence that PRC2 can simultaneously engage nonadjacent nucleosome pairs. The demonstration of PRC2's ability to bridge noncontiguous chromosomal segments furthers our understanding of how Polycomb complexes spread epigenetic modifications and compact chromatin.}, number={48}, journal={Proceedings of the National Academy of Sciences}, publisher={Proceedings of the National Academy of Sciences}, author={Leicher, Rachel and Ge, Eva J. and Lin, Xingcheng and Reynolds, Matthew J. and Xie, Wenjun and Walz, Thomas and Zhang, Bin and Muir, Tom W. and Liu, Shixin}, year={2020}, month={Nov}, pages={30465–30475} } @article{lin_schafer_lu_jin_chen_chen_onuchic_wolynes_2019, title={Forging tools for refining predicted protein structures}, volume={116}, ISSN={0027-8424 1091-6490}, url={http://dx.doi.org/10.1073/pnas.1900778116}, DOI={10.1073/pnas.1900778116}, abstractNote={Refining predicted protein structures with all-atom molecular dynamics simulations is one route to producing, entirely by computational means, structural models of proteins that rival in quality those that are determined by X-ray diffraction experiments. Slow rearrangements within the compact folded state, however, make routine refinement of predicted structures by unrestrained simulations infeasible. In this work, we draw inspiration from the fields of metallurgy and blacksmithing, where practitioners have worked out practical means of controlling equilibration by mechanically deforming their samples. We describe a two-step refinement procedure that involves identifying collective variables for mechanical deformations using a coarse-grained model and then sampling along these deformation modes in all-atom simulations. Identifying those low-frequency collective modes that change the contact map the most proves to be an effective strategy for choosing which deformations to use for sampling. The method is tested on 20 refinement targets from the CASP12 competition and is found to induce large structural rearrangements that drive the structures closer to the experimentally determined structures during relatively short all-atom simulations of 50 ns. By examining the accuracy of side-chain rotamer states in subensembles of structures that have varying degrees of similarity to the experimental structure, we identified the reorientation of aromatic side chains as a step that remains slow even when encouraging global mechanical deformations in the all-atom simulations. Reducing the side-chain rotamer isomerization barriers in the all-atom force field is found to further speed up refinement.}, number={19}, journal={Proceedings of the National Academy of Sciences}, publisher={Proceedings of the National Academy of Sciences}, author={Lin, Xingcheng and Schafer, Nicholas P. and Lu, Wei and Jin, Shikai and Chen, Xun and Chen, Mingchen and Onuchic, José N. and Wolynes, Peter G.}, year={2019}, month={Apr}, pages={9400–9409} } @article{bhattacharya_lin_2019, title={Recent Advances in Computational Protocols Addressing Intrinsically Disordered Proteins}, volume={9}, ISSN={2218-273X}, url={http://dx.doi.org/10.3390/biom9040146}, DOI={10.3390/biom9040146}, abstractNote={Intrinsically disordered proteins (IDP) are abundant in the human genome and have recently emerged as major therapeutic targets for various diseases. Unlike traditional proteins that adopt a definitive structure, IDPs in free solution are disordered and exist as an ensemble of conformations. This enables the IDPs to signal through multiple signaling pathways and serve as scaffolds for multi-protein complexes. The challenge in studying IDPs experimentally stems from their disordered nature. Nuclear magnetic resonance (NMR), circular dichroism, small angle X-ray scattering, and single molecule Förster resonance energy transfer (FRET) can give the local structural information and overall dimension of IDPs, but seldom provide a unified picture of the whole protein. To understand the conformational dynamics of IDPs and how their structural ensembles recognize multiple binding partners and small molecule inhibitors, knowledge-based and physics-based sampling techniques are utilized in-silico, guided by experimental structural data. However, efficient sampling of the IDP conformational ensemble requires traversing the numerous degrees of freedom in the IDP energy landscape, as well as force-fields that accurately model the protein and solvent interactions. In this review, we have provided an overview of the current state of computational methods for studying IDP structure and dynamics and discussed the major challenges faced in this field.}, number={4}, journal={Biomolecules}, publisher={MDPI AG}, author={Bhattacharya, Supriyo and Lin, Xingcheng}, year={2019}, month={Apr}, pages={146} } @article{lin_kulkarni_bocci_schafer_roy_tsai_he_chen_rajagopalan_mooney_et al._2019, title={Structural and Dynamical Order of a Disordered Protein: Molecular Insights into Conformational Switching of PAGE4 at the Systems Level}, volume={9}, ISSN={2218-273X}, url={http://dx.doi.org/10.3390/biom9020077}, DOI={10.3390/biom9020077}, abstractNote={Folded proteins show a high degree of structural order and undergo (fairly constrained) collective motions related to their functions. On the other hand, intrinsically disordered proteins (IDPs), while lacking a well-defined three-dimensional structure, do exhibit some structural and dynamical ordering, but are less constrained in their motions than folded proteins. The larger structural plasticity of IDPs emphasizes the importance of entropically driven motions. Many IDPs undergo function-related disorder-to-order transitions driven by their interaction with specific binding partners. As experimental techniques become more sensitive and become better integrated with computational simulations, we are beginning to see how the modest structural ordering and large amplitude collective motions of IDPs endow them with an ability to mediate multiple interactions with different partners in the cell. To illustrate these points, here, we use Prostate-associated gene 4 (PAGE4), an IDP implicated in prostate cancer (PCa) as an example. We first review our previous efforts using molecular dynamics simulations based on atomistic AWSEM to study the conformational dynamics of PAGE4 and how its motions change in its different physiologically relevant phosphorylated forms. Our simulations quantitatively reproduced experimental observations and revealed how structural and dynamical ordering are encoded in the sequence of PAGE4 and can be modulated by different extents of phosphorylation by the kinases HIPK1 and CLK2. This ordering is reflected in changing populations of certain secondary structural elements as well as in the regularity of its collective motions. These ordered features are directly correlated with the functional interactions of WT-PAGE4, HIPK1-PAGE4 and CLK2-PAGE4 with the AP-1 signaling axis. These interactions give rise to repeated transitions between (high HIPK1-PAGE4, low CLK2-PAGE4) and (low HIPK1-PAGE4, high CLK2-PAGE4) cell phenotypes, which possess differing sensitivities to the standard PCa therapies, such as androgen deprivation therapy (ADT). We argue that, although the structural plasticity of an IDP is important in promoting promiscuous interactions, the modulation of the structural ordering is important for sculpting its interactions so as to rewire with agility biomolecular interaction networks with significant functional consequences.}, number={2}, journal={Biomolecules}, publisher={MDPI AG}, author={Lin, Xingcheng and Kulkarni, Prakash and Bocci, Federico and Schafer, Nicholas and Roy, Susmita and Tsai, Min-Yeh and He, Yanan and Chen, Yihong and Rajagopalan, Krithika and Mooney, Steven and et al.}, year={2019}, month={Feb}, pages={77} } @article{lin_noel_wang_ma_onuchic_2018, title={Atomistic simulations indicate the functional loop-to-coiled-coil transition in influenza hemagglutinin is not downhill}, volume={115}, ISSN={0027-8424 1091-6490}, url={http://dx.doi.org/10.1073/pnas.1805442115}, DOI={10.1073/pnas.1805442115}, abstractNote={SignificanceInfluenza hemagglutinin (HA) is the viral membrane protein that guides entry of flu viruses into host cells. A global refolding of the stem domain of HA,HA2, is crucial to successful viral membrane fusion, but the molecular mechanism relating this conformational change ofHA2to its fusogenic properties remains unclear. We use molecular dynamics simulations to quantify the thermodynamic importance of the B loop domain for driving the overallHA2rearrangement. We find that the B loop’s loop-to-coiled-coil refolding is not strongly downhill and thus is a possible target for therapeutics. A buried hydrophilic amino acid is implicated in destabilizing the coiled coil, and the sequence divergence at this position may indicate functional differences between group 1 and 2 HAs.}, number={34}, journal={Proceedings of the National Academy of Sciences}, publisher={Proceedings of the National Academy of Sciences}, author={Lin, Xingcheng and Noel, Jeffrey K. and Wang, Qinghua and Ma, Jianpeng and Onuchic, José N.}, year={2018}, month={Jul} } @article{lin_roy_jolly_bocci_schafer_tsai_chen_he_grishaev_weninger_et al._2018, title={PAGE4 and Conformational Switching: Insights from Molecular Dynamics Simulations and Implications for Prostate Cancer}, volume={430}, ISSN={0022-2836}, url={http://dx.doi.org/10.1016/j.jmb.2018.05.011}, DOI={10.1016/j.jmb.2018.05.011}, abstractNote={Prostate-associated gene 4 (PAGE4) is an intrinsically disordered protein implicated in prostate cancer. Thestress-response kinase homeodomain-interacting protein kinase 1 (HIPK1) phosphorylates two residues in PAGE4, serine 9 and threonine 51. Phosphorylation of these two residues facilitates the interaction of PAGE4 with activator protein-1 (AP-1) transcription factor complex to potentiate AP-1's activity. In contrast, hyperphosphorylation of PAGE4 by CDC-like kinase 2 (CLK2) attenuates this interaction with AP-1. Small-angleX-ray scattering and single-molecule fluorescence resonance energy transfer measurements have shown that PAGE4 expands upon hyperphosphorylation and that this expansion is localized to its N-terminal half. To understand the interactions underlying this structural transition, we performed molecular dynamics simulations using Atomistic AWSEM, a multi-scale molecular model that combines atomistic and coarse-grained simulation approaches. Our simulations show that electrostatic interactions drive transient formation of an N-terminal loop, the destabilization of which accounts for the dramatic change in size upon hyperphosphorylation. Phosphorylation also changes the preference of secondary structure formation of the PAGE4 ensemble, which leads to a transition between states that display different degrees of disorder. Finally, we construct a mechanism-based mathematical model that allows us to capture the interactions ofdifferent phosphoforms of PAGE4 with AP-1 and its downstream target, the androgen receptor (AR)-a key therapeutic target in prostate cancer. Our model predicts intracellular oscillatory dynamics of HIPK1-PAGE4, CLK2-PAGE4, and AR activity, indicating phenotypic heterogeneity in an isogenic cell population. Thus, conformational switching of PAGE4 may potentially affect the efficiency of therapeutically targeting AR activity.}, number={16}, journal={Journal of Molecular Biology}, publisher={Elsevier BV}, author={Lin, Xingcheng and Roy, Susmita and Jolly, Mohit Kumar and Bocci, Federico and Schafer, Nicholas P. and Tsai, Min-Yeh and Chen, Yihong and He, Yanan and Grishaev, Alexander and Weninger, Keith and et al.}, year={2018}, month={Aug}, pages={2422–2438} } @article{lin_roy_jolly_bocci_schafer_tsai_chen_he_grishaev_weninger_et al._2018, title={PAGE4 and Conformational Switching: Insights from Molecular Dynamics Simulations and Implications for Prostate Cancer}, volume={2}, url={https://doi.org/10.1101/264010}, DOI={10.1101/264010}, abstractNote={AbstractProstate-Associated Gene 4 (PAGE4) is a disordered protein implicated in the progression of prostate cancer. PAGE4 can be phosphorylated at two residue sites by Homeodomain-Interacting Protein Kinase 1 (HIPK1) to facilitate its binding to the Activator Protein-1 (AP-1) transcription factor. In contrast, a further hyperphosphorylation of PAGE4 by CDC-Like Kinase 2 (CLK2) reduces its binding affinity to AP-1, thus affecting the androgen receptor (AR) activity. Both SAXS and smFRET experiments have shown a structural expansion of PAGE4 upon hyperphosphorylation and a significant increase in size at its N-terminal half than that at its C-terminus. To understand the molecular mechanism underlying this structural transition, we performed a series of constant temperature molecular dynamics simulations using Atomistic AWSEM — a multi-scale molecular model combining detailed atomistic and coarse-grained simulation approaches. Our simulations show that electrostatic interaction drives a transient formation of an N-terminal loop, which causes the change in size for different phosphorylated forms of PAGE4. Phosphorylation also changes the preference of secondary structure formation of PAGE4, which signifies a transition between states that display different degree of disorder. Finally, we construct a mechanism-based mathematical model that allows us to capture the interactions of different forms of PAGE4 with AP-1 and AR, a key therapeutic target in prostate cancer. Our model predicts intracellular oscillatory dynamics of HIPK1-PAGE4, CLK2-PAGE4 and AR activity, indicating phenotypic heterogeneity in an isogenic cell population. Thus, conformational switching among different forms of PAGE4 may potentially affect the efficiency of therapeutic targeting of AR.}, publisher={Cold Spring Harbor Laboratory}, author={Lin, Xingcheng and Roy, Susmita and Jolly, Mohit Kumar and Bocci, Federico and Schafer, Nicholas and Tsai, Min-Yeh and Chen, Yihong and He, Yanan and Grishaev, Alexander and Weninger, Keith and et al.}, year={2018}, month={Feb} } @article{chen_lin_lu_schafer_onuchic_wolynes_2018, title={Template-Guided Protein Structure Prediction and Refinement Using Optimized Folding Landscape Force Fields}, volume={14}, ISSN={1549-9618 1549-9626}, url={http://dx.doi.org/10.1021/acs.jctc.8b00683}, DOI={10.1021/acs.jctc.8b00683}, abstractNote={When good structural templates can be identified, template-based modeling is the most reliable way to predict the tertiary structure of proteins. In this study, we combine template-based modeling with a realistic coarse-grained force field, AWSEM, that has been optimized using the principles of energy landscape theory. The Associative memory, Water mediated, Structure and Energy Model (AWSEM) is a coarse-grained force field having both transferable tertiary interactions and knowledge-based local-in-sequence interaction terms. We incorporate template information into AWSEM by introducing soft collective biases to the template structures, resulting in a model that we call AWSEM-Template. Structure prediction tests on eight targets, four of which are in the low sequence identity "twilight zone" of homology modeling, show that AWSEM-Template can achieve high-resolution structure prediction. Our results also confirm that using a combination of AWSEM and a template-guided potential leads to more accurate prediction of protein structures than simply using a template-guided potential alone. Free energy profile analyses demonstrate that the soft collective biases to the template effectively increase funneling toward native-like structures while still allowing significant flexibility so as to allow for correction of discrepancies between the target structure and the template. A further stage of refinement using all-atom molecular dynamics augmented with soft collective biases to the structures predicted by AWSEM-Template leads to a further improvement of both backbone and side-chain accuracy by maintaining sufficient flexibility but at the same time discouraging unproductive unfolding events often seen in unrestrained all-atom refinement simulations. The all-atom refinement simulations also reduce patches of frustration of the initial predictions. Some of the backbones found among the structures produced during the initial coarse-grained prediction step already have CE-RMSD values of less than 3 Å with 90% or more of the residues aligned to the experimentally solved structure for all targets. All-atom structures generated during the following all-atom refinement simulations, which started from coarse-grained structures that were chosen without reference to any knowledge about the native structure, have CE-RMSD values of less than 2.5 Å with 90% or more of the residues aligned for 6 out of 8 targets. Clustering low energy structures generated during the initial coarse-grained annealing picks out reliably structures that are within 1 Å of the best sampled structures in 5 out of 8 cases. After the all-atom refinement, structures that are within 1 Å of the best sampled structures can be selected using a simple algorithm based on energetic features alone in 7 out of 8 cases.}, number={11}, journal={Journal of Chemical Theory and Computation}, publisher={American Chemical Society (ACS)}, author={Chen, Mingchen and Lin, Xingcheng and Lu, Wei and Schafer, Nicholas P. and Onuchic, José N. and Wolynes, Peter G.}, year={2018}, month={Sep}, pages={6102–6116} } @article{yao_wang_liao_chen_pan_li_zhang_lin_wang_luo_et al._2017, title={Quantum Image Processing and Its Application to Edge Detection: Theory and Experiment}, volume={7}, ISSN={2160-3308}, url={http://dx.doi.org/10.1103/PhysRevX.7.031041}, DOI={10.1103/PhysRevX.7.031041}, abstractNote={Processing of digital images is continuously gaining in volume and relevance, with concomitant demands on data storage, transmission and processing power. Encoding the image information in quantum-mechanical systems instead of classical ones and replacing classical with quantum information processing may alleviate some of these challenges. By encoding and processing the image information in quantum-mechanical systems, we here demonstrate the framework of quantum image processing, where a pure quantum state encodes the image information: we encode the pixel values in the probability amplitudes and the pixel positions in the computational basis states. Our quantum image representation reduces the required number of qubits compared to existing implementations, and we present image processing algorithms that provide exponential speed-up over their classical counterparts. For the commonly used task of detecting the edge of an image, we propose and implement a quantum algorithm that completes the task with only one single-qubit operation, independent of the size of the image. This demonstrates the potential of quantum image processing for highly efficient image and video processing in the big data era.}, number={3}, journal={Physical Review X}, publisher={American Physical Society (APS)}, author={Yao, Xi-Wei and Wang, Hengyan and Liao, Zeyang and Chen, Ming-Cheng and Pan, Jian and Li, Jun and Zhang, Kechao and Lin, Xingcheng and Wang, Zhehui and Luo, Zhihuang and et al.}, year={2017}, month={Sep} } @article{lin_noel_wang_ma_onuchic_2016, title={Lowered pH Leads to Fusion Peptide Release and a Highly Dynamic Intermediate of Influenza Hemagglutinin}, volume={120}, ISSN={1520-6106 1520-5207}, url={http://dx.doi.org/10.1021/acs.jpcb.6b06775}, DOI={10.1021/acs.jpcb.6b06775}, abstractNote={Hemagglutinin (HA), the membrane-bound fusion protein of the influenza virus, enables the entry of virus into host cells via a structural rearrangement. There is strong evidence that the primary trigger for this rearrangement is the low pH environment of a late endosome. To understand the structural basis and the dynamic consequences of the pH trigger, we employed explicit-solvent molecular dynamics simulations to investigate the initial stages of the HA transition. Our results indicate that lowered pH destabilizes HA and speeds up the dissociation of the fusion peptides (FPs). A buried salt bridge between the N-terminus and Asp1122 of HA stem domain locks the FPs and may act as one of the pH sensors. In line with recent observations from simplified protein models, we find that, after the dissociation of FPs, a structural order-disorder transition in a loop connecting the central coiled-coil to the C-terminal domains produces a highly mobile HA. This motion suggests the existence of a long-lived asymmetric or "symmetry-broken" intermediate during the HA conformational change. This intermediate conformation is consistent with models of hemifusion, and its early formation during the conformational change has implications for the aggregation seen in HA activity.}, number={36}, journal={The Journal of Physical Chemistry B}, publisher={American Chemical Society (ACS)}, author={Lin, Xingcheng and Noel, Jeffrey K. and Wang, Qinghua and Ma, Jianpeng and Onuchic, José N.}, year={2016}, month={Sep}, pages={9654–9660} } @article{chen_lin_lu_onuchic_wolynes_2016, title={Protein Folding and Structure Prediction from the Ground Up II: AAWSEM for α/β Proteins}, volume={121}, ISSN={1520-6106 1520-5207}, url={http://dx.doi.org/10.1021/acs.jpcb.6b09347}, DOI={10.1021/acs.jpcb.6b09347}, abstractNote={The atomistic associative memory, water mediated, structure and energy model (AAWSEM) is an efficient coarse-grained force field with transferable tertiary interactions that incorporates local in sequence energetic biases using structural information derived from all-atom simulations of long segments of the protein. For α helical proteins, the accuracy of structure prediction using AAWSEM has been established previously. In this article, we examine the capability of AAWSEM to predict the structure of α/β proteins. We also elaborate on an iterative approach that uses the structures from a first round of AAWSEM simulation as fragment memories. This iterative scheme improves the quality of the structure prediction and makes the free energy profile more funneled toward native configurations. We explore the use of clustering analyses as a way of evaluating the confidence in various structure prediction models. Clustering using a local relative order parameter (mutual Q) of the predicted structural ensemble turns out to be optimal. The tightest cluster according to mutual Q generally has the most correctly folded structure. Since there is no bioinformatic input, AAWSEM amounts to an ab initio protein structure prediction method that combines the efficiency of coarse-grained simulations with the local structural accuracy that can be achieved from all-atom simulations.}, number={15}, journal={The Journal of Physical Chemistry B}, publisher={American Chemical Society (ACS)}, author={Chen, Mingchen and Lin, Xingcheng and Lu, Wei and Onuchic, José N. and Wolynes, Peter G.}, year={2016}, month={Nov}, pages={3473–3482} } @article{chen_lin_zheng_onuchic_wolynes_2016, title={Protein Folding and Structure Prediction from the Ground Up: The Atomistic Associative Memory, Water Mediated, Structure and Energy Model}, volume={120}, ISSN={1520-6106 1520-5207}, url={http://dx.doi.org/10.1021/acs.jpcb.6b02451}, DOI={10.1021/acs.jpcb.6b02451}, abstractNote={The associative memory, water mediated, structure and energy model (AWSEM) is a coarse-grained force field with transferable tertiary interactions that incorporates local in sequence energetic biases using bioinformatically derived structural information about peptide fragments with locally similar sequences that we call memories. The memory information from the protein data bank (PDB) database guides proper protein folding. The structural information about available sequences in the database varies in quality and can sometimes lead to frustrated free energy landscapes locally. One way out of this difficulty is to construct the input fragment memory information from all-atom simulations of portions of the complete polypeptide chain. In this paper, we investigate this approach first put forward by Kwac and Wolynes in a more complete way by studying the structure prediction capabilities of this approach for six α-helical proteins. This scheme which we call the atomistic associative memory, water mediated, structure and energy model (AAWSEM) amounts to an ab initio protein structure prediction method that starts from the ground up without using bioinformatic input. The free energy profiles from AAWSEM show that atomistic fragment memories are sufficient to guide the correct folding when tertiary forces are included. AAWSEM combines the efficiency of coarse-grained simulations on the full protein level with the local structural accuracy achievable from all-atom simulations of only parts of a large protein. The results suggest that a hybrid use of atomistic fragment memory and database memory in structural predictions may well be optimal for many practical applications.}, number={33}, journal={The Journal of Physical Chemistry B}, publisher={American Chemical Society (ACS)}, author={Chen, Mingchen and Lin, Xingcheng and Zheng, Weihua and Onuchic, José N. and Wolynes, Peter G.}, year={2016}, month={May}, pages={8557–8565} } @article{lin_eddy_noel_whitford_wang_ma_onuchic_2014, title={Order and disorder control the functional rearrangement of influenza hemagglutinin}, volume={111}, ISSN={0027-8424 1091-6490}, url={http://dx.doi.org/10.1073/pnas.1412849111}, DOI={10.1073/pnas.1412849111}, abstractNote={Significance Influenza hemagglutinin (HA), a viral surface glycoprotein, undergoes a critical and large conformational rearrangement to promote fusion of the viral membrane with the host membrane. Unlike the variable receptor binding domain HA 1 , the coiled-coil domain HA 2 is highly conserved, making HA 2 a promising target for therapeutics. Furthermore, the structural similarity between influenza HA 2 and other viral fusion proteins, including that of HIV, makes HA 2 a valuable model system. We build a model using information from only the prefusion and postfusion configurations of HA 2 and use molecular dynamics simulations to characterize the structural ensembles found during the conformational transition. We find that local unfolding facilitates interaction of HA 2 with the host membrane and enables a quasi-stable asymmetric intermediate during the transition. }, number={33}, journal={Proceedings of the National Academy of Sciences}, publisher={Proceedings of the National Academy of Sciences}, author={Lin, Xingcheng and Eddy, Nathanial R. and Noel, Jeffrey K. and Whitford, Paul C. and Wang, Qinghua and Ma, Jianpeng and Onuchic, José N.}, year={2014}, month={Jul}, pages={12049–12054} } @article{yao_chen_mu_pan_yang_lin_lian_wang_2010, title={Measurement method of logical gate in bulk spin quantum computer}, volume={32}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-77957596622&partnerID=MN8TOARS}, DOI={10.3963/j.issn.1671-4431.2010.15.034}, number={15}, journal={Wuhan Ligong Daxue Xuebao/Journal of Wuhan University of Technology}, author={Yao, X.-W. and Chen, Z.-W. and Mu, X.-Y. and Pan, J. and Yang, C. and Lin, X.-C. and Lian, J.-H. and Wang, X.-W.}, year={2010}, pages={142–145} } @article{bi-rong_qin_xiao-yang_xing-cheng_chun_jian_zhong_2010, title={Subspace quantum process tomography via nuclear magnetic resonance}, volume={59}, ISSN={1000-3290 1000-3290}, url={http://dx.doi.org/10.7498/aps.59.6837}, DOI={10.7498/aps.59.6837}, abstractNote={Experimental investigation of subspace quantum process tomography in three-spin system was implemented via nuclear magnetic resonance. A quantum process was characterized by measuring a complete set of input states and corresponding outputs. The method using ancillary qubit remarkably reduces the number of the initial input states. And the pulse sequences used in this paper have fewer J-coupling evolutions. The experiment time was shortened and quantum decoherence of the system was weakened efficiently.}, number={10}, journal={Acta Physica Sinica}, publisher={Acta Physica Sinica, Chinese Physical Society and Institute of Physics, Chinese Academy of Sciences}, author={Bi-Rong, Zeng and Qin, Liu and Xiao-Yang, Mu and Xing-Cheng, Lin and Chun, Yang and Jian, Pan and Zhong, Chen}, year={2010}, pages={6837} }